Year: 2026
Type: preprint
Abstract: Artificial intelligence (AI) for domain science demands large, well-structured training corpora that integrate experimental data with not only explicit knowledge but also tacit expertise underlying scientific decisions. However, the tacit knowledge regarding practical reasoning, assumptions, failed attempts, parameter choices, and interpretive judgment is often held by authors and unpublished, hindering its use for AI development. Here, we propose Agentic Paper, a large language model (LLM)-enabled, author-curated scientific publishing framework that organizes these resources into a structured Agentic Paper package accessible through LLM-based interfaces, enabling the integration of connected, AI-ready data, explicit knowledge, and tacit expertise. Within Agentic Paper, the LLM serves as an interactive reasoning and orchestration layer that connects knowledge content with raw and processed data, figures, methodological details, metadata, code, and author-provided interpretation. Case studies in materials synthesis and characterization demonstrate how the LLM-enabled framework supports questioning, data visualization and inspection, numerical verification, and preparation of AI-ready datasets. By combining author-based organization of scientific data and knowledge, Agentic Paper provides a scalable pathway toward provenance-rich training corpora and more reliable AI-enabled scientific workflows.
Source: ChemRxiv
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7216433901